Volumetric grid is widely used for 3D deep learning due to its regularity. However the use of relatively lower order local approximation functions such as piece-wise constant function (occupancy grid) or piece-wise linear function (distance field) to approximate 3D shape means that it needs a very high-resolution grid to represent finer geometry details, which could be memory and computationally inefficient. In this work, we propose the PointGrid, a 3D convolutional network that incorporates a constant number of points within each grid cell thus allowing the network to learn higher order local approximation functions that could better represent the local geometry shape details. With experiments on popular shape recognition benchmarks, PointGrid demonstrates state-of-the-art performance over existing deep learning methods on both classification and segmentation.
{"title":"PointGrid: A Deep Network for 3D Shape Understanding","authors":"Truc Le, Y. Duan","doi":"10.1109/CVPR.2018.00959","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00959","url":null,"abstract":"Volumetric grid is widely used for 3D deep learning due to its regularity. However the use of relatively lower order local approximation functions such as piece-wise constant function (occupancy grid) or piece-wise linear function (distance field) to approximate 3D shape means that it needs a very high-resolution grid to represent finer geometry details, which could be memory and computationally inefficient. In this work, we propose the PointGrid, a 3D convolutional network that incorporates a constant number of points within each grid cell thus allowing the network to learn higher order local approximation functions that could better represent the local geometry shape details. With experiments on popular shape recognition benchmarks, PointGrid demonstrates state-of-the-art performance over existing deep learning methods on both classification and segmentation.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"96 1","pages":"9204-9214"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74373639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Maoke Yang, Kun Yu, Chi Zhang, Zhiwei Li, Kuiyuan Yang
Semantic image segmentation is a basic street scene understanding task in autonomous driving, where each pixel in a high resolution image is categorized into a set of semantic labels. Unlike other scenarios, objects in autonomous driving scene exhibit very large scale changes, which poses great challenges for high-level feature representation in a sense that multi-scale information must be correctly encoded. To remedy this problem, atrous convolution[14]was introduced to generate features with larger receptive fields without sacrificing spatial resolution. Built upon atrous convolution, Atrous Spatial Pyramid Pooling (ASPP)[2] was proposed to concatenate multiple atrous-convolved features using different dilation rates into a final feature representation. Although ASPP is able to generate multi-scale features, we argue the feature resolution in the scale-axis is not dense enough for the autonomous driving scenario. To this end, we propose Densely connected Atrous Spatial Pyramid Pooling (DenseASPP), which connects a set of atrous convolutional layers in a dense way, such that it generates multi-scale features that not only cover a larger scale range, but also cover that scale range densely, without significantly increasing the model size. We evaluate DenseASPP on the street scene benchmark Cityscapes[4] and achieve state-of-the-art performance.
{"title":"DenseASPP for Semantic Segmentation in Street Scenes","authors":"Maoke Yang, Kun Yu, Chi Zhang, Zhiwei Li, Kuiyuan Yang","doi":"10.1109/CVPR.2018.00388","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00388","url":null,"abstract":"Semantic image segmentation is a basic street scene understanding task in autonomous driving, where each pixel in a high resolution image is categorized into a set of semantic labels. Unlike other scenarios, objects in autonomous driving scene exhibit very large scale changes, which poses great challenges for high-level feature representation in a sense that multi-scale information must be correctly encoded. To remedy this problem, atrous convolution[14]was introduced to generate features with larger receptive fields without sacrificing spatial resolution. Built upon atrous convolution, Atrous Spatial Pyramid Pooling (ASPP)[2] was proposed to concatenate multiple atrous-convolved features using different dilation rates into a final feature representation. Although ASPP is able to generate multi-scale features, we argue the feature resolution in the scale-axis is not dense enough for the autonomous driving scenario. To this end, we propose Densely connected Atrous Spatial Pyramid Pooling (DenseASPP), which connects a set of atrous convolutional layers in a dense way, such that it generates multi-scale features that not only cover a larger scale range, but also cover that scale range densely, without significantly increasing the model size. We evaluate DenseASPP on the street scene benchmark Cityscapes[4] and achieve state-of-the-art performance.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"12 1","pages":"3684-3692"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76684713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Loc Huynh, Weikai Chen, Shunsuke Saito, Jun Xing, Koki Nagano, Andrew Jones, P. Debevec, Hao Li
We present a learning-based approach for synthesizing facial geometry at medium and fine scales from diffusely-lit facial texture maps. When applied to an image sequence, the synthesized detail is temporally coherent. Unlike current state-of-the-art methods [17, 5], which assume "dark is deep", our model is trained with measured facial detail collected using polarized gradient illumination in a Light Stage [20]. This enables us to produce plausible facial detail across the entire face, including where previous approaches may incorrectly interpret dark features as concavities such as at moles, hair stubble, and occluded pores. Instead of directly inferring 3D geometry, we propose to encode fine details in high-resolution displacement maps which are learned through a hybrid network adopting the state-of-the-art image-to-image translation network [29] and super resolution network [43]. To effectively capture geometric detail at both mid- and high frequencies, we factorize the learning into two separate sub-networks, enabling the full range of facial detail to be modeled. Results from our learning-based approach compare favorably with a high-quality active facial scanhening technique, and require only a single passive lighting condition without a complex scanning setup.
{"title":"Mesoscopic Facial Geometry Inference Using Deep Neural Networks","authors":"Loc Huynh, Weikai Chen, Shunsuke Saito, Jun Xing, Koki Nagano, Andrew Jones, P. Debevec, Hao Li","doi":"10.1109/CVPR.2018.00877","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00877","url":null,"abstract":"We present a learning-based approach for synthesizing facial geometry at medium and fine scales from diffusely-lit facial texture maps. When applied to an image sequence, the synthesized detail is temporally coherent. Unlike current state-of-the-art methods [17, 5], which assume \"dark is deep\", our model is trained with measured facial detail collected using polarized gradient illumination in a Light Stage [20]. This enables us to produce plausible facial detail across the entire face, including where previous approaches may incorrectly interpret dark features as concavities such as at moles, hair stubble, and occluded pores. Instead of directly inferring 3D geometry, we propose to encode fine details in high-resolution displacement maps which are learned through a hybrid network adopting the state-of-the-art image-to-image translation network [29] and super resolution network [43]. To effectively capture geometric detail at both mid- and high frequencies, we factorize the learning into two separate sub-networks, enabling the full range of facial detail to be modeled. Results from our learning-based approach compare favorably with a high-quality active facial scanhening technique, and require only a single passive lighting condition without a complex scanning setup.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"52 1","pages":"8407-8416"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76900806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
True Price, Johannes L. Schönberger, Zhen Wei, M. Pollefeys, Jan-Michael Frahm
Image-based 3D reconstruction for Internet photo collections has become a robust technology to produce impressive virtual representations of real-world scenes. However, several fundamental challenges remain for Structure-from-Motion (SfM) pipelines, namely: the placement and reconstruction of transient objects only observed in single views, estimating the absolute scale of the scene, and (suprisingly often) recovering ground surfaces in the scene. We propose a method to jointly address these remaining open problems of SfM. In particular, we focus on detecting people in individual images and accurately placing them into an existing 3D model. As part of this placement, our method also estimates the absolute scale of the scene from object semantics, which in this case constitutes the height distribution of the population. Further, we obtain a smooth approximation of the ground surface and recover the gravity vector of the scene directly from the individual person detections. We demonstrate the results of our approach on a number of unordered Internet photo collections, and we quantitatively evaluate the obtained absolute scene scales.
{"title":"Augmenting Crowd-Sourced 3D Reconstructions Using Semantic Detections","authors":"True Price, Johannes L. Schönberger, Zhen Wei, M. Pollefeys, Jan-Michael Frahm","doi":"10.1109/CVPR.2018.00206","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00206","url":null,"abstract":"Image-based 3D reconstruction for Internet photo collections has become a robust technology to produce impressive virtual representations of real-world scenes. However, several fundamental challenges remain for Structure-from-Motion (SfM) pipelines, namely: the placement and reconstruction of transient objects only observed in single views, estimating the absolute scale of the scene, and (suprisingly often) recovering ground surfaces in the scene. We propose a method to jointly address these remaining open problems of SfM. In particular, we focus on detecting people in individual images and accurately placing them into an existing 3D model. As part of this placement, our method also estimates the absolute scale of the scene from object semantics, which in this case constitutes the height distribution of the population. Further, we obtain a smooth approximation of the ground surface and recover the gravity vector of the scene directly from the individual person detections. We demonstrate the results of our approach on a number of unordered Internet photo collections, and we quantitatively evaluate the obtained absolute scene scales.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"96 1","pages":"1926-1935"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80971681","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Visual object tracking has been a fundamental topic in recent years and many deep learning based trackers have achieved state-of-the-art performance on multiple benchmarks. However, most of these trackers can hardly get top performance with real-time speed. In this paper, we propose the Siamese region proposal network (Siamese-RPN) which is end-to-end trained off-line with large-scale image pairs. Specifically, it consists of Siamese subnetwork for feature extraction and region proposal subnetwork including the classification branch and regression branch. In the inference phase, the proposed framework is formulated as a local one-shot detection task. We can pre-compute the template branch of the Siamese subnetwork and formulate the correlation layers as trivial convolution layers to perform online tracking. Benefit from the proposal refinement, traditional multi-scale test and online fine-tuning can be discarded. The Siamese-RPN runs at 160 FPS while achieving leading performance in VOT2015, VOT2016 and VOT2017 real-time challenges.
{"title":"High Performance Visual Tracking with Siamese Region Proposal Network","authors":"Bo Li, Junjie Yan, Wei Wu, Zheng Zhu, Xiaolin Hu","doi":"10.1109/CVPR.2018.00935","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00935","url":null,"abstract":"Visual object tracking has been a fundamental topic in recent years and many deep learning based trackers have achieved state-of-the-art performance on multiple benchmarks. However, most of these trackers can hardly get top performance with real-time speed. In this paper, we propose the Siamese region proposal network (Siamese-RPN) which is end-to-end trained off-line with large-scale image pairs. Specifically, it consists of Siamese subnetwork for feature extraction and region proposal subnetwork including the classification branch and regression branch. In the inference phase, the proposed framework is formulated as a local one-shot detection task. We can pre-compute the template branch of the Siamese subnetwork and formulate the correlation layers as trivial convolution layers to perform online tracking. Benefit from the proposal refinement, traditional multi-scale test and online fine-tuning can be discarded. The Siamese-RPN runs at 160 FPS while achieving leading performance in VOT2015, VOT2016 and VOT2017 real-time challenges.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"1 1","pages":"8971-8980"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83111186","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Light-field imaging is based on images taken on a regular grid. Thus, high-quality 3D reconstructions are obtainable by analyzing orientations in epipolar plane images (EPIs). Unfortunately, such data only allows to evaluate one side of the object. Moreover, a constant intensity along each orientation is mandatory for most of the approaches. This paper presents a novel method which allows to reconstruct depth information from data acquired with a circular camera motion, termed circular light fields. With this approach it is possible to determine the full 360° view of target objects. Additionally, circular light fields allow retrieving depth from datasets acquired with telecentric lenses, which is not possible with linear light fields. The proposed method finds trajectories of 3D points in the EPIs by means of a modified Hough transform. For this purpose, binary EPI-edge images are used, which not only allow to obtain reliable depth information, but also overcome the limitation of constant intensity along trajectories. Experimental results on synthetic and real datasets demonstrate the quality of the proposed algorithm.
{"title":"Robust Hough Transform Based 3D Reconstruction from Circular Light Fields","authors":"A. Vianello, J. Ackermann, M. Diebold, B. Jähne","doi":"10.1109/CVPR.2018.00765","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00765","url":null,"abstract":"Light-field imaging is based on images taken on a regular grid. Thus, high-quality 3D reconstructions are obtainable by analyzing orientations in epipolar plane images (EPIs). Unfortunately, such data only allows to evaluate one side of the object. Moreover, a constant intensity along each orientation is mandatory for most of the approaches. This paper presents a novel method which allows to reconstruct depth information from data acquired with a circular camera motion, termed circular light fields. With this approach it is possible to determine the full 360° view of target objects. Additionally, circular light fields allow retrieving depth from datasets acquired with telecentric lenses, which is not possible with linear light fields. The proposed method finds trajectories of 3D points in the EPIs by means of a modified Hough transform. For this purpose, binary EPI-edge images are used, which not only allow to obtain reliable depth information, but also overcome the limitation of constant intensity along trajectories. Experimental results on synthetic and real datasets demonstrate the quality of the proposed algorithm.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"105 1","pages":"7327-7335"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80943086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Despoina Paschalidou, Ali O. Ulusoy, Carolin Schmitt, L. Gool, Andreas Geiger
In this paper, we consider the problem of reconstructing a dense 3D model using images captured from different views. Recent methods based on convolutional neural networks (CNN) allow learning the entire task from data. However, they do not incorporate the physics of image formation such as perspective geometry and occlusion. Instead, classical approaches based on Markov Random Fields (MRF) with ray-potentials explicitly model these physical processes, but they cannot cope with large surface appearance variations across different viewpoints. In this paper, we propose RayNet, which combines the strengths of both frameworks. RayNet integrates a CNN that learns view-invariant feature representations with an MRF that explicitly encodes the physics of perspective projection and occlusion. We train RayNet end-to-end using empirical risk minimization. We thoroughly evaluate our approach on challenging real-world datasets and demonstrate its benefits over a piece-wise trained baseline, hand-crafted models as well as other learning-based approaches.
{"title":"RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials","authors":"Despoina Paschalidou, Ali O. Ulusoy, Carolin Schmitt, L. Gool, Andreas Geiger","doi":"10.1109/CVPR.2018.00410","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00410","url":null,"abstract":"In this paper, we consider the problem of reconstructing a dense 3D model using images captured from different views. Recent methods based on convolutional neural networks (CNN) allow learning the entire task from data. However, they do not incorporate the physics of image formation such as perspective geometry and occlusion. Instead, classical approaches based on Markov Random Fields (MRF) with ray-potentials explicitly model these physical processes, but they cannot cope with large surface appearance variations across different viewpoints. In this paper, we propose RayNet, which combines the strengths of both frameworks. RayNet integrates a CNN that learns view-invariant feature representations with an MRF that explicitly encodes the physics of perspective projection and occlusion. We train RayNet end-to-end using empirical risk minimization. We thoroughly evaluate our approach on challenging real-world datasets and demonstrate its benefits over a piece-wise trained baseline, hand-crafted models as well as other learning-based approaches.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"52 1","pages":"3897-3906"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89074136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The increasing popularity of computational light field (LF) cameras has necessitated the need for tackling motion blur which is a ubiquitous phenomenon in hand-held photography. The state-of-the-art method for blind deblurring of LFs of general 3D scenes is limited to handling only downsampled LF, both in spatial and angular resolution. This is due to the computational overhead involved in processing data-hungry full-resolution 4D LF altogether. Moreover, the method warrants high-end GPUs for optimization and is ineffective for wide-angle settings and irregular camera motion. In this paper, we introduce a new blind motion deblurring strategy for LFs which alleviates these limitations significantly. Our model achieves this by isolating 4D LF motion blur across the 2D subaperture images, thus paving the way for independent deblurring of these subaperture images. Furthermore, our model accommodates common camera motion parameterization across the subaperture images. Consequently, blind deblurring of any single subaperture image elegantly paves the way for cost-effective non-blind deblurring of the other subaperture images. Our approach is CPU-efficient computationally and can effectively deblur full-resolution LFs.
{"title":"Divide and Conquer for Full-Resolution Light Field Deblurring","authors":"M. Mohan, A. Rajagopalan","doi":"10.1109/CVPR.2018.00672","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00672","url":null,"abstract":"The increasing popularity of computational light field (LF) cameras has necessitated the need for tackling motion blur which is a ubiquitous phenomenon in hand-held photography. The state-of-the-art method for blind deblurring of LFs of general 3D scenes is limited to handling only downsampled LF, both in spatial and angular resolution. This is due to the computational overhead involved in processing data-hungry full-resolution 4D LF altogether. Moreover, the method warrants high-end GPUs for optimization and is ineffective for wide-angle settings and irregular camera motion. In this paper, we introduce a new blind motion deblurring strategy for LFs which alleviates these limitations significantly. Our model achieves this by isolating 4D LF motion blur across the 2D subaperture images, thus paving the way for independent deblurring of these subaperture images. Furthermore, our model accommodates common camera motion parameterization across the subaperture images. Consequently, blind deblurring of any single subaperture image elegantly paves the way for cost-effective non-blind deblurring of the other subaperture images. Our approach is CPU-efficient computationally and can effectively deblur full-resolution LFs.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"30 1","pages":"6421-6429"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90308082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ke Xian, Chunhua Shen, ZHIGUO CAO, Hao Lu, Yang Xiao, Ruibo Li, Zhenbo Luo
In this paper we study the problem of monocular relative depth perception in the wild. We introduce a simple yet effective method to automatically generate dense relative depth annotations from web stereo images, and propose a new dataset that consists of diverse images as well as corresponding dense relative depth maps. Further, an improved ranking loss is introduced to deal with imbalanced ordinal relations, enforcing the network to focus on a set of hard pairs. Experimental results demonstrate that our proposed approach not only achieves state-of-the-art accuracy of relative depth perception in the wild, but also benefits other dense per-pixel prediction tasks, e.g., metric depth estimation and semantic segmentation.
{"title":"Monocular Relative Depth Perception with Web Stereo Data Supervision","authors":"Ke Xian, Chunhua Shen, ZHIGUO CAO, Hao Lu, Yang Xiao, Ruibo Li, Zhenbo Luo","doi":"10.1109/CVPR.2018.00040","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00040","url":null,"abstract":"In this paper we study the problem of monocular relative depth perception in the wild. We introduce a simple yet effective method to automatically generate dense relative depth annotations from web stereo images, and propose a new dataset that consists of diverse images as well as corresponding dense relative depth maps. Further, an improved ranking loss is introduced to deal with imbalanced ordinal relations, enforcing the network to focus on a set of hard pairs. Experimental results demonstrate that our proposed approach not only achieves state-of-the-art accuracy of relative depth perception in the wild, but also benefits other dense per-pixel prediction tasks, e.g., metric depth estimation and semantic segmentation.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"21 1","pages":"311-320"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84502200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The current underwater image formation model descends from atmospheric dehazing equations where attenuation is a weak function of wavelength. We recently showed that this model introduces significant errors and dependencies in the estimation of the direct transmission signal because underwater, light attenuates in a wavelength-dependent manner. Here, we show that the backscattered signal derived from the current model also suffers from dependencies that were previously unaccounted for. In doing so, we use oceanographic measurements to derive the physically valid space of backscatter, and further show that the wideband coefficients that govern backscatter are different than those that govern direct transmission, even though the current model treats them to be the same. We propose a revised equation for underwater image formation that takes these differences into account, and validate it through in situ experiments underwater. This revised model might explain frequent instabilities of current underwater color reconstruction models, and calls for the development of new methods.
{"title":"A Revised Underwater Image Formation Model","authors":"D. Akkaynak, T. Treibitz","doi":"10.1109/CVPR.2018.00703","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00703","url":null,"abstract":"The current underwater image formation model descends from atmospheric dehazing equations where attenuation is a weak function of wavelength. We recently showed that this model introduces significant errors and dependencies in the estimation of the direct transmission signal because underwater, light attenuates in a wavelength-dependent manner. Here, we show that the backscattered signal derived from the current model also suffers from dependencies that were previously unaccounted for. In doing so, we use oceanographic measurements to derive the physically valid space of backscatter, and further show that the wideband coefficients that govern backscatter are different than those that govern direct transmission, even though the current model treats them to be the same. We propose a revised equation for underwater image formation that takes these differences into account, and validate it through in situ experiments underwater. This revised model might explain frequent instabilities of current underwater color reconstruction models, and calls for the development of new methods.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"11 1","pages":"6723-6732"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86274766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：